The observations for the validation were taken from 2015-01-02 00:00:00 to 2023-12-30 23:00:00.
Remember that we have on a daily scale the variables
sfcWind, tas, pr,
tasmax, tasmin and psl and in a
monthly scale clt, rsdt,rsds as a
predictors. We also have the month , hour, sun’s elevation & azimuth
and the daily daylight amount in seconds as a predictors too.
| Metric | xgboost | cnn | naive | lstm |
|---|---|---|---|---|
| mae | 0.64 | 0.82 | 0.83 | 0.71 |
| cor | 0.99 | 0.99 | 0.98 | 0.99 |
| ratio_of_sd | 0.99 | 1.01 | 0.98 | 0.98 |
| KGE | 0.98 | 0.98 | 0.98 | 0.98 |
| amplitude_mae | 1.03 | 1.09 | 1.95 | 1.07 |
| maximum_difference | 1.49 | 1.43 | 1.44 | 1.38 |
| sign_correlation | 0.89 | 0.79 | 0.91 | 0.87 |
| extreme_correlation | 0.81 | 0.76 | 0.71 | 0.84 |
| qqplot_mae | 0.06 | 0.35 | 0.09 | 0.38 |
| acf_mae | 0.02 | 0.04 | 0.03 | 0.01 |
| extremogram_mae | 0.02 | 0.02 | 0.01 | 0.01 |
Important: Right now we are only estimating the upper tail
extremogram. Currently we didn’t find a way to estimate the two tales at
the same time. We are using quant = .97